A novel statistical analysis and autoencoder driven intelligent intrusion detection approach

Ieracitano, Cosimo; Adeel, Ahsan; Morabito, Francesco Carlo; Hussain, Amir

doi:10.1016/j.neucom.2019.11.016

Cited by 192 publications

(94 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In what follows, the details of the resulting design are presented. [27] Difference between real and Neural networks-ARIMA Supervised predicted consumption Ieracitano et al [34] Statistical features Autoencoder base LSTM Unsupervised Ramchandran et al [36] Raw images and detected edges Convolutional DNN-based Unsupervised autoencoder and LSTM Janetzko et al [46] Power spectrum Clustering and visual analytics Unsupervised Ma el al. [47] Standard deviation of temporal FCD-POD-LSE Unsupervised coefficients Cui and Wang [48] Power consumption time series Polynomial regression and Semi-supervised Gaussian distribution Buzau et al [52] Historic and non-sequential power data DNN-based LSTM and MLP Supervised Lin and Claridge [54] Power consumption deviation between measured Unsupervised and temperature and simulated consumption Araya et al [55] Contextual/behavioral features Detecting incomplete data in Unsupervised sliding window Liu et al [56] Power and temperature Lambda architecture Supervised Current paper Micro-moment consumption and DNN and rule-based algorithm Supervised occupancy data Fig.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…In [23], Yan proposes a deep anomaly detection to identify gas turbine combustor anomalies based on two principal stages: (i) it uses a DNN for learning characteristic representations extracted from multivariate time-series sensor records; and (ii) it deploys a one-class classification for modeling normal variables in the training feature set and helps in identifying anomalies through capturing the variables that do not fall into the normal class. In [34], a deep learning approach based on an autoencoder architecture is proposed for intrusion detection. It relies on using statistical data analysis with a deep autoencoder-based long short-term memory (LSTM) for extracting optimal, robust, and highly correlated characteristics.…”

Section: Machine Learning-based Techniquesmentioning

confidence: 99%

“…In recent years, the promising progress in developing machine learning algorithms has substantiated their efficacy in various research fields. Starting from the fact that learning-based techniques may be useful to identify rare occurrences or observations (outliers) that arouse suspicion, their deployment for anomaly detection for several applications becomes prevalent, e.g., intrusion detection [34], fraud detection [35], abnormality detection in video surveillance [36], turbine combustor anomaly detection [23]. Moreover, machine learning algorithms can be combined with adequate feature extraction approaches to enhance their efficiency.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Approach for Detecting Anomalous Energy Consumption Based on Micro-Moments and Deep Neural Networks

et al. 2020

View full text Add to dashboard Cite

Nowadays, analyzing, detecting, and visualizing abnormal power consumption behavior of householders are among the principal challenges in identifying ways to reduce power consumption. This paper introduces a new solution to detect energy consumption anomalies based on extracting micro-moment features using a rule-based model. The latter is used to draw out load characteristics using daily intent-driven moments of user consumption actions. Besides micro-moment features extraction, we also experiment with a deep neural network architecture for efficient abnormality detection and classification. In the following, a novel anomaly visualization technique is introduced that is based on a scatter representation of the micro-moment classes, and hence providing consumers an easy solution to understand their abnormal behavior. Moreover, in order to validate the proposed system, a new energy consumption dataset at appliance level is also designed through a measurement campaign carried out at Qatar University Energy Lab, namely, Qatar University dataset. Experimental results on simulated and real datasets collected at two regions, which have extremely different climate conditions, confirm that the proposed deep micro-moment architecture outperforms other machine learning algorithms and can effectively detect anomalous patterns. For example, 99.58% accuracy and 97.85% F1 score have been achieved under Qatar University dataset. These promising results establish the efficacy of the proposed deep micro-moment solution for detecting abnormal energy consumption, promoting energy efficiency behaviors, and reducing wasted energy.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Section: Machine Learning-based Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Approach for Detecting Anomalous Energy Consumption Based on Micro-Moments and Deep Neural Networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Kunang et al [46] proposed an automatic feature extraction technique based on autoencoder (i.e., a type of artificial neural network aimed to learn efficient data encodings, by following an unsupervised strategy) and support vector machine for the intrusion detection task. Recently, Ieracitano et al [47] combined the autoencoder technique with a statistical analysis, in order to define an intrusion detection approach.…”

Section: Related Workmentioning

confidence: 99%

A Local Feature Engineering Strategy to Improve Network Anomaly Detection

et al. 2020

View full text Add to dashboard Cite

The dramatic increase in devices and services that has characterized modern societies in recent decades, boosted by the exponential growth of ever faster network connections and the predominant use of wireless connection technologies, has materialized a very crucial challenge in terms of security. The anomaly-based intrusion detection systems, which for a long time have represented some of the most efficient solutions to detect intrusion attempts on a network, have to face this new and more complicated scenario. Well-known problems, such as the difficulty of distinguishing legitimate activities from illegitimate ones due to their similar characteristics and their high degree of heterogeneity, today have become even more complex, considering the increase in the network activity. After providing an extensive overview of the scenario under consideration, this work proposes a Local Feature Engineering (LFE) strategy aimed to face such problems through the adoption of a data preprocessing strategy that reduces the number of possible network event patterns, increasing at the same time their characterization. Unlike the canonical feature engineering approaches, which take into account the entire dataset, it operates locally in the feature space of each single event. The experiments conducted on real-world data showed that this strategy, which is based on the introduction of new features and the discretization of their values, improves the performance of the canonical state-of-the-art solutions.

show abstract

“…Regarding to the importance of computer network nowadays and our ever growing dependency on them has made the security manner is so crucial and listed in the top of priorities for many domain of interests [6][7][8]. One of the major concerns that has been tackled in the information security community recently is the intrusion detection systems (IDS) [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

A hybrid method of genetic algorithm and support vector machine for intrusion detection

Tally¹,

Amintoosi

2021

IJECE

View full text Add to dashboard Cite

With the development of web applications nowadays, intrusions represent a crucial aspect in terms of violating the security policies. Intrusions can be defined as a specific change in the normal behavior of the network operations that intended to violate the security policies of a particular network and affect its performance. Recently, several researchers have examined the capabilities of machine learning techniques in terms of detecting intrusions. One of the important issues behind using the machine learning techniques lies on employing proper set of features. Since the literature has shown diversity of feature types, there is a vital demand to apply a feature selection approach in order to identify the most appropriate features for intrusion detection. This study aims to propose a hybrid method of Genetic Algorithm and Support Vector Machine. GA has been as a feature selection in order to select the best features, while SVM has been used as a classification method to categorize the behavior into normal and intrusion based on the selected features from GA. A benchmark dataset of intrusions (NSS-KDD) has been in the experiment. In addition, the proposed method has been compared with the traditional SVM. Results showed that GA has significantly improved the SVM classification by achieving 0.927 of f-measure.

show abstract

A novel statistical analysis and autoencoder driven intelligent intrusion detection approach

Cited by 192 publications

References 25 publications

A Novel Approach for Detecting Anomalous Energy Consumption Based on Micro-Moments and Deep Neural Networks

A Novel Approach for Detecting Anomalous Energy Consumption Based on Micro-Moments and Deep Neural Networks

A Local Feature Engineering Strategy to Improve Network Anomaly Detection

A hybrid method of genetic algorithm and support vector machine for intrusion detection

Contact Info

Product

Resources

About